Semantic segmentation for prostate cancer grading by convolutional neural networks

Certain pathology workflows, such as classification and grading of prostate adenocarcinoma according to the Gleason grade scheme, stand to gain speed and objectivity by incorporating contemporary digital image analysis methods. We compiled a dataset of 513 high resolution image tiles from primary prostate adenocarcinoma wherein individual glands and stroma were demarcated and graded by hand. With this unique dataset, we tested four Convolutional Neural Network architectures including FCN-8s, two SegNet variants, and multi-scale U-Net for performance in semantic segmentation of high- and low-grade tumors. In a 5-fold cross-validation experiment, the FCN-8s architecture achieved a mIOU of 0.759 and an accuracy of 0.87, while the less complex U-Net architecture achieved a mIOU of 0.738 and accuracy of 0.885. The FCN-8s architecture applied to whole slide images not used for training achieved a mIOU of 0.857 in annotated tumor foci with a multiresolution processing time averaging 11 minutes per slide. The three architectures tested on whole slides all achieved areas under the Receiver Operating Characteristic curve near 1, strongly demonstrating the suitability of semantic segmentation Convolutional Neural Networks for detecting and grading prostate cancer foci in radical prostatectomies.

[1]  Fabio A. González,et al.  Cascaded ensemble of convolutional neural networks and handcrafted features for mitosis detection , 2014, Medical Imaging.

[2]  Aleksey Boyko,et al.  Detecting Cancer Metastases on Gigapixel Pathology Images , 2017, ArXiv.

[3]  Arkadiusz Gertych,et al.  A Machine Learning Approach to Identify Prostate Cancer Areas in Complex Histological Images , 2014 .

[4]  Arkadiusz Gertych,et al.  Machine learning approaches to analyze histological images of tissues from radical prostatectomies , 2015, Comput. Medical Imaging Graph..

[5]  Luc Van Gool,et al.  The Pascal Visual Object Classes Challenge: A Retrospective , 2014, International Journal of Computer Vision.

[6]  Jin Tae Kwak,et al.  Lumen-based detection of prostate cancer via convolutional neural networks , 2017, Medical Imaging.

[7]  Xin Qi,et al.  Computer aided analysis of prostate histopathology images to support a refined Gleason grading system , 2017, Medical Imaging.

[8]  Ewa Pietka,et al.  Information Technologies in Biomedicine, Volume 3 , 2014 .

[9]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[10]  Claes Lundström,et al.  Towards grading gleason score using generically trained deep convolutional neural networks , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[11]  B. van Ginneken,et al.  Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis , 2016, Scientific Reports.

[12]  Wei Liu,et al.  Towards Large-Scale Histopathological Image Analysis: Hashing-Based Image Retrieval , 2015, IEEE Transactions on Medical Imaging.

[13]  Anant Madabhushi,et al.  Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent , 2017, Scientific Reports.

[14]  Erik Reinhard,et al.  Color Transfer between Images , 2001, IEEE Computer Graphics and Applications.

[15]  Clément Farabet,et al.  Torch7: A Matlab-like Environment for Machine Learning , 2011, NIPS 2011.

[16]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[17]  Mahadev Satyanarayanan,et al.  OpenSlide: A vendor-neutral software foundation for digital pathology , 2013, Journal of pathology informatics.

[18]  Chris Bakal,et al.  Microenvironmental Heterogeneity Parallels Breast Cancer Progression: A Histology–Genomic Integration Analysis , 2016, PLoS medicine.

[19]  Mats Andersson,et al.  Convolutional neural networks for an automatic classification of prostate tissue slides with high-grade Gleason score , 2017, Medical Imaging.

[20]  Fei-Fei Li,et al.  What's the Point: Semantic Segmentation with Point Supervision , 2015, ECCV.

[21]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[22]  Catarina Eloy,et al.  Classification of breast cancer histology images using Convolutional Neural Networks , 2017, PloS one.

[23]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Anant Madabhushi,et al.  Emerging Themes in Image Informatics and Molecular Analysis for Digital Pathology. , 2016, Annual review of biomedical engineering.

[25]  Arkadiusz Gertych,et al.  A Multi-scale U-Net for Semantic Segmentation of Histological Images from Radical Prostatectomies , 2017, AMIA.

[26]  Ron Kikinis,et al.  Large scale digital prostate pathology image analysis combining feature extraction and deep neural network , 2017, ArXiv.

[27]  Xiang Zhang,et al.  OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks , 2013, ICLR.

[28]  Eric Cosatto,et al.  Classification of mitotic figures with convolutional neural networks and seeded blob features , 2013, Journal of pathology informatics.

[29]  Lippincott Williams Wilkins,et al.  The American journal of surgical pathology , 1977 .

[30]  B. Delahunt,et al.  The 2014 International Society of Urological Pathology (ISUP) Consensus Conference on Gleason Grading of Prostatic Carcinoma: Definition of Grading Patterns and Proposal for a New Grading System , 2015, The American journal of surgical pathology.

[31]  Fang Yang,et al.  New breast cancer prognostic factors identified by computer-aided image analysis of HE stained histopathology images , 2015, Scientific Reports.